Trojan detection from network traffic data is crucial for safeguarding networks against covert infiltration and potential data breaches. Deep learning (DL) techniques can play a pivotal role in detecting trojans from network traffic data by learning complex patterns and anomalies indicative of malicious behavior, thus enhancing detection accuracy and efficiency. This technique is pivotal in the context of data security, specifically in next-generation network architecture for its ability to effectively detect complex and evolving cyber threats, such as Trojan horse traffic, ensuring robust network protection. The research gap in detecting network Trojans lies in developing techniques capable of efficiently identifying stealthy and polymorphic variants while minimizing false positives. This study focuses on trojan detection from network traffic data, crucial for network security. Deep learning, specifically a combination of Convolutional neural networks (CNNs) and Bidirectional Long Short-Term Memory (BiLSTM) networks, is proposed to enhance accuracy and efficiency by learning complex patterns indicative of malicious behavior. Our proposed approach extracts features using CNNs to capture spatial dependencies and utilizes BiLSTM networks to process sequential dependencies, achieving 99% accuracy in trojan detection on real-world datasets. We validated this performance by comparing with previous approaches to ensure robustness in a common dataset. Making our work available open-source on, can enhance its accessibility and promote future research opportunities in Trojan Network Detection. After this work, we will work on detecting trojan networks from our institute’s network data and will release the trojan network dataset, as there is a gap in open-source trojan network datasets.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Deep Learning-Based Trojan Detection in Network Traffic: A CNN-BiLSTM Approach


    Beteiligte:
    Hoque, Md Mozammal (Autor:in) / Alam, Khorshed (Autor:in) / Monir, Md Fahad (Autor:in) / Tarek Habib, Md (Autor:in)


    Erscheinungsdatum :

    07.10.2024


    Format / Umfang :

    691278 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Deep reinforcement learning traffic signal control poisoning attack method based on Trojan horse attack

    XU DONGWEI / WANG DA / LI CHENGBIN | Europäisches Patentamt | 2022

    Freier Zugriff

    FPGA Hardware Trojan Detection: Golden-Free Machine Learning Approach

    Ghimire, Ashutosh / Amsaad, Fathi / Hossain, Tanvir et al. | IEEE | 2023


    Research on Ensemble Classification Model of Trojan Traffic Detection

    Lan, Jinghong / Liu, Shengli / Wu, Shuang et al. | British Library Online Contents | 2015